© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8736
    Prev
    Next
    INDEX
    Explanations

    to register or implement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strup
    -0.08
    Ø©
    -0.08
    esso
    -0.07
     presumably
    -0.07
     anyone
    -0.07
     Äijâu
    -0.07
     chắc
    -0.07
    yers
    -0.07
    ation
    -0.07
    ัà¸ĩหว
    -0.07
    POSITIVE LOGITS
    åģļä¸ĢäºĽ
    0.08
    æīįèĥ½è¾¾åĪ°
    0.08
     reconsider
    0.08
     пÑĢидеÑĤÑģÑı
    0.08
    æŶæĹ¥
    0.08
    è¦ģèĢĥèĻij
    0.07
    è¿ĺå¾Ĺ
    0.07
    æŶæīį
    0.07
    æĽ´å¤ļçļĦ
    0.07
    æŁIJäºĽ
    0.07
    Activations Density 0.038%

    No Known Activations